论文信息 - Petascale System Management Experiences

Petascale System Management Experiences

Petascale HPC systems are among the largest systems in the world. Intrepid, one such system, is a 40,000 node, 556 teraflop Blue Gene/P system that has been deployed at Argonne National Laboratory. In this paper, we provide some background about the system and our administration experiences. In particular, due to the scale of the system, we have faced a variety of issues, some surprising to us, that are not common in the commodity world. We discuss our expectations, these issues, and approaches we have used to address them.

[1] George L.-T. Chiu,et al. Overview of the Blue Gene/L system architecture , 2005, IBM J. Res. Dev..

[2] Jonathan Appavoo,et al. Project Kittyhawk: building a global-scale computer: Blue Gene/P as a generic computing platform , 2008, OPSR.

[3] John P. Rouillard. Real-time Log File Analysis Using the Simple Event Correlator (SEC) , 2004, LISA.

[4] Meeta Sharma Gupta,et al. Performance implications of periodic checkpointing on large-scale cluster systems , 2005, 19th IEEE International Parallel and Distributed Processing Symposium.

[5] Narayan Desai,et al. MPI Cluster System Software , 2004, PVM/MPI.

[6] Chris McEniry,et al. Moobi: A Thin Server Management System Using BitTorrent , 2007, LISA.

[7] Andreas Holzman. Recent Advances in Parallel Virtual Machine and Message Passing Interface , 1997, Lecture Notes in Computer Science.